HISTOGRAM-BASED SMOKE SEGMENTATION IN FOREST FIRE DETECTION SYSTEM

By Damir Krstinic, Darko Stipanicev, Toni Jakovcevic. Information Technology and Control, 2009

724 citations recorded by the source corpus.

A focus of this paper is a pixel level analysis and segmentation of smoke colored pixels for the automated forest fire detection. Variations in the smoke color tones, environmental illumination, atmospheric conditions and low quality of the images of wide outdoor area make smoke detection a complex task. In order to find an efficient combination of a color space and pixel level smoke segmentation algorithm, several color space transformations are evaluated by measuring separability between smoke and non-smoke classes of pixels. However, exhaustive evaluation of the histogram-based smoke segmentation algorithms in different color spaces suggests that the peak performance is the distinctive feature of the algorithm itself rather than the algorithm-color space combination.

Subfields: Computer Vision and Pattern Recognition, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/e4f61c3898d4392d9e4fbfa16d993bb94daefb49

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety, Risk, Reliability and Quality

Citations in the corpus

Efficient Deep CNN-Based Fire Detection and Localization in Video Surveillance Applications (2019, methodology): “[9] examined the dynamic behavior of fires 74 using RGB and HSI color models and proposed a deci- 75 sion rule-assisted fire detection approach, which uses the 76 irregular properties of fire for detection.”
A Forest Fire Detection System Based on Ensemble Learning (2021, background): “[9] proposed an RGB (red, green, blue) model based chromatic and disorder measurement for extracting fire-pixels in the video.”
Video fire detection - Review (2013, methodology): “The majority of the color-based approaches in VFD make use of RGB color space, sometimes in combination with HSI/HSV saturation [10,24, 27,28].”
Convolutional Neural Networks Based Fire Detection in Surveillance Videos (2018, background): “The pixel-level meth- 46 ods [5], [6] are fast due to usage of pixel-wise features such 47 as colors and flickers, however, their performance is not 48 attractive as such methods can be easily biased.”
Wavelet based real-time smoke detection in video (2005, methodology): “In [ 11 ], a similar method is used which is based on a color model for flame and smoke.”